Downloads · 30 days
13
2% of all-time downloads
muzero-V2
richard151111/muzero-V2
muzero-V2 is a reinforcement learning model from richard151111. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
MuZero agent for the Pokémon Trading Card Game (PTCG), trained via hybrid ISMCTS (belief sampling) + collapsed chance nodes for stochastic transitions.
All-time downloads
631
Public
Repo size
645 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pkl7 GB · 59%
At a glance
- Task
- Reinforcement Learning
- License
- mit
- Access
- Public
- Created
- Aug 3, 2026
- Updated
- Aug 21, 2026
- SHA
- d846376b
Model card
From the Hugging Face model README
PTCG MuZero Agent
MuZero agent for the Pokémon Trading Card Game (PTCG), trained via hybrid ISMCTS (belief sampling) + collapsed chance nodes for stochastic transitions.
Architecture
| Component | Details |
|---|---|
| Representation | Transformer encoder (4 layers, d=256) |
| Prediction | Two-head MLP (policy + value) |
| Dynamics | Residual MLP with stochastic branch |
| Card embedding | Learned (64d) + static CSV features (48d) |
| Search | Gumbel MuZero + ISMCTS (4 determinisations) |
| Interpretability | 5 linear probing classifiers |
Training
- Framework: JAX / Flax
- Devices: 8× GPU (data-parallel via jax.pmap)
- Step: 342,000
- Batch size: 64
- LR: 0.0003
Files
| File | Content |
|---|---|
muzero.safetensors | MuZero network weights (h + f + g + probes) |
deck_builder.safetensors | Deck builder policy weights |
config.json | Full training configuration |
- Task
- Reinforcement Learning
- License
- mit
- Languages
- en
- Created
- Aug 3, 2026
- Updated
- Aug 21, 2026